P-Value Calculator
Turn a test statistic into a p-value. Choose z, t, chi-square or F, enter the statistic and its degrees of freedom, and pick a left, right or two-tailed test. You also get the critical values at common significance levels and a chart with the p-value area shaded.
For F: numerator df (between groups)
Within groups / error df
Chi-square and F tests are usually right-tailed
How to use the P-Value Calculator
- Choose the statistic: z, t, chi-square or F.
- Enter the value of your test statistic and its degrees of freedom (two for F).
- Pick the tail: two-tailed for ≠ alternatives, right or left for one-sided tests. Chi-square and F tests are normally right-tailed.
- Read the p-value and whether it is significant at your α.
- Compare with the critical values table and the shaded chart.
How the p-value is calculated
| Statistic | Typical test | Two-tailed p | Right-tailed p |
|---|---|---|---|
| z | z-test for means or proportions | 2 × (1 − Φ(|z|)) | 1 − Φ(z) |
| t (df) | t-tests, regression coefficients | 2 × P(Tdf ≥ |t|) | P(Tdf ≥ t) |
| χ² (df) | Goodness of fit, independence | 2 × min(left, right) | P(χ²df ≥ x) |
| F (df1, df2) | ANOVA, comparing variances | 2 × min(left, right) | P(Fdf1,df2 ≥ x) |
A left-tailed p-value is the area to the left of the statistic, the CDF itself. The calculator evaluates the normal CDF and the t, chi-square and F CDFs through the regularized incomplete gamma and beta functions.
Common critical values
| Distribution | α = 0.10 | α = 0.05 | α = 0.01 |
|---|---|---|---|
| z, two-tailed | ±1.645 | ±1.960 | ±2.576 |
| z, one-tailed | 1.282 | 1.645 | 2.326 |
| t, df = 10, two-tailed | ±1.812 | ±2.228 | ±3.169 |
| χ², df = 1, right-tailed | 2.706 | 3.841 | 6.635 |
| χ², df = 3, right-tailed | 6.251 | 7.815 | 11.345 |
| F(2, 20), right-tailed | 2.589 | 3.493 | 5.849 |
Frequently asked questions
What is a p-value?
A p-value is the probability of getting a test statistic at least as extreme as the one observed, assuming the null hypothesis is true. Small p-values (below your significance level α, often 0.05) mean the data would be surprising if the null hypothesis held, so you reject it.
How do I get a p-value from a z-score?
For a two-tailed test, p = 2 × (1 − Φ(|z|)), where Φ is the standard normal CDF. For a right-tailed test p = 1 − Φ(z) and for a left-tailed test p = Φ(z). For example z = 1.96 gives a two-tailed p of about 0.05.
How do I get a p-value from a t statistic?
Use the t distribution with the test's degrees of freedom: two-tailed p = 2 × P(T ≥ |t|). With df = 15, t = 2.1 gives p ≈ 0.053. As df grows the t distribution approaches the normal, so the p-value approaches the z-test value.
Should a chi-square or F test be one-tailed or two-tailed?
Chi-square goodness-of-fit and independence tests and ANOVA F tests are right-tailed: only large values of the statistic count as evidence against the null hypothesis. Two-tailed versions are used only in special cases, such as testing whether a variance is different from a given value in either direction.
What is the difference between a p-value and a critical value?
They are two views of the same decision. The critical value is the cutoff statistic for a chosen α; the p-value is the smallest α at which your statistic would be significant. If |statistic| is beyond the critical value, p is below α.
Is p < 0.05 always significant?
Only if 0.05 is the significance level you chose in advance. Fields use different levels (0.10, 0.01, 0.005). A significant p-value also says nothing about the size or practical importance of an effect, and a large p-value does not prove the null hypothesis is true.
How accurate are these p-values?
They are computed from the regularized incomplete gamma and beta functions, which give the exact normal, t, chi-square and F distribution tails to many decimal places, including very small p-values shown in scientific notation.